Saved in:
Bibliographic Details
Main Authors: Abzaliev, Artem, Espinosa, Humberto Pérez, Mihalcea, Rada
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.18739
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911857951899648
author Abzaliev, Artem
Espinosa, Humberto Pérez
Mihalcea, Rada
author_facet Abzaliev, Artem
Espinosa, Humberto Pérez
Mihalcea, Rada
contents Similar to humans, animals make extensive use of verbal and non-verbal forms of communication, including a large range of audio signals. In this paper, we address dog vocalizations and explore the use of self-supervised speech representation models pre-trained on human speech to address dog bark classification tasks that find parallels in human-centered tasks in speech recognition. We specifically address four tasks: dog recognition, breed identification, gender classification, and context grounding. We show that using speech embedding representations significantly improves over simpler classification baselines. Further, we also find that models pre-trained on large human speech acoustics can provide additional performance boosts on several tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2404_18739
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Dog Bark Decoding: Leveraging Human Speech Processing for Automated Bark Classification
Abzaliev, Artem
Espinosa, Humberto Pérez
Mihalcea, Rada
Computation and Language
Similar to humans, animals make extensive use of verbal and non-verbal forms of communication, including a large range of audio signals. In this paper, we address dog vocalizations and explore the use of self-supervised speech representation models pre-trained on human speech to address dog bark classification tasks that find parallels in human-centered tasks in speech recognition. We specifically address four tasks: dog recognition, breed identification, gender classification, and context grounding. We show that using speech embedding representations significantly improves over simpler classification baselines. Further, we also find that models pre-trained on large human speech acoustics can provide additional performance boosts on several tasks.
title Towards Dog Bark Decoding: Leveraging Human Speech Processing for Automated Bark Classification
topic Computation and Language
url https://arxiv.org/abs/2404.18739